Stephan Linzbach, Dimitar Dimitrov, Laura Kallmeyer, Kilian Evang, Hajira Jabeen, Stefan Dietze. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Large Scale Global Optimization (LSGO) is interesting for its applications in machine learning, e.g. in deep learning or knowledge graph embeddings. Evolutionary algorithms (EA) have been found efficient in solving complex optimization problems. However, the performance of conventional EAs degrades with the increasing number of decision variables due to the lack of scalability. This paper proposes a scalable, parallel, distributed and hybrid EA named Distributed Scalable Shade-BatScalable Shade Bat (DistSSB) to solve LSGO problems. DistSSB is inspired by the exploration capability of the SHADE algorithm and exploitation feature of the Bat algorithm (BA). To achieve scalability, DistSSB is implemented using the popular distributed in-memory framework, Apache Spark. DistSSB distributes its population into multiple sub-populations using the island model. Each sub-population is independently evolved using SHADE or BA. After the migration interval, the best solutions are broadcasted employing the mesh topology. We have compared the scalability, efficiency, and efficacy of DistSSB with SHADE-ILS (CEC-2018 Winner) and GL-SHADE algorithm on the CEC-2013 LSGO benchmark function suite.For most functions, DistSSB has obtained better optimization results in lesser execution time as compared to SHADE-ILS and GL-SHADE. We have tested and shown the scalability of DistSSB for up to "one million" dimensions, whereas SHADE-ILS and GLSHADE fail to scale up for larger problems.

This paper presents DistRDF2ML, the generic, scalable, and distributed framework for creating in-memory data preprocessing pipelines for Spark-based machine learning on RDF knowledge graphs. This framework introduces software modules that transform large-scale RDF data into ML-ready fixed-length numeric feature vectors. The developed modules are optimized to the multi-modal nature of knowledge graphs. DistRDF2ML provides aligned software design and usage principles as common data science stacks that offer an easy-to-use package for creating machine learning pipelines. The modules used in the pipeline, the hyper-parameters and the results are exported as a semantic structure that can be used to enrich the original knowledge graph. The semantic representation of metadata and machine learning results offers the advantage of increasing the machine learning pipelines' reusability, explainability, and reproducibility. The entire framework of DistRDF2ML is open source, integrated into the holistic SANSA stack, documented in scala-docs, and covered by unit tests. DistRDF2ML demonstrates its scalable design across different processing power configurations and (hyper-)parameter setups within various experiments. The framework brings the three worlds of knowledge graph engineers, distributed computation developers, and data scientists closer together and offers all of them the creation of explainable ML pipelines using a few lines of code.

51

Big Data Analytics is a crucial component of the Big Data paradigm and deals with the extraction of knowledge from the enormous amount of data. As the number of Big Data related methods, tools, frameworks, and solutions is growing, there is a need to systematize the knowledge about the domain. Moreover, as this domain is rapidly involving, it is difficult to keep up to date with its latest and most efficient technologies; and this is thereby especially challenging for countries which have so far suffered from a lack of infrastructure in Big Data.

As the number of Big Data related methods, tools, frameworks, and solutions is growing, there is a need to classify and make available the knowledge related to this domain. This is especially useful for countries which, so far, have suffered from some lack of infra-structure in Big Data. In this article, we describe the deployment of an open online platform gathering lectures and resources, from multiple partnered European institutions, tailored for West Balkan students with a particular focus on local Big Data challenges.

Cooking is an endeavour unique to humans. It is mainly considered an art requiring culinary intuition acquired through practice. The preparation of food is a complex and subjective process that makes it challenging to determine underlying rules for automation. In this paper, we present AutoChef, the first open-source autonomous recipe generator. AutoChef extracts the data from existing recipes using natural language processing, learns the combination of ingredients, preparation actions and cooking instructions, and autonomously generates the recipes. Furthermore, AutoChef uses Genetic Programming to represent and evolve the recipes. The fitness of recipes is designed to evaluate the combination of ingredients, actions and cooking-processes learned from the existing recipe data. Finally, the resulting recipes are translated back into text format and evaluated by human experts.

227

Increasing data volumes have extensively increased application possibilities. However, accessing this data in an ad hoc manner remains an unsolved problem due to the diversity of data management approaches, formats and storage frameworks, resulting in the need to effectively access and process distributed heterogeneous data at scale. For years, Semantic Web techniques have addressed data integration challenges with practical knowledge representation models and ontology-based mappings. Leveraging these techniques, we provide a solution enabling uniform access to large, heterogeneous data sources, without enforcing centralization; thus realizing the vision of a Semantic Data Lake. In this paper, we define the core concepts underlying this vision and the architectural requirements that systems implementing it need to fulfill. Squerall, an example of such a system, is an extensible framework built on top of state-of-the-art Big Data technologies. We focus on Squerall's distributed query execution techniques and strategies, empirically evaluating its performance throughout its various sub-phases.

Squerall is a tool that allows the querying of heterogeneous, large-scale data sources by leveraging state-of-the-art Big Data processing engines: Spark and Presto. Queries are posed on-demand against a Data Lake, i.e., directly on the original data sources without requiring prior data transformation. We showcase Squerall's ability to query five different data sources, including inter alia the popular Cassandra and MongoDB. In particular, we demonstrate how it can jointly query heterogeneous data sources, and how interested developers can easily extend it to support additional data sources. Graphical user interfaces (GUIs) are offered to support users in (1) building intra-source queries, and (2) creating required input files.

SUMMARY: Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs' nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programing and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies. AVAILABILITY AND IMPLEMENTATION: BioKEEN and PyKEEN are open source Python packages publicly available under the MIT License at https://github.com/SmartDataAnalytics/BioKEEN and https://github.com/SmartDataAnalytics/PyKEEN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.